Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4250 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.9337. Min Act: -0.1700
Data Index: 8652805 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.7775. Min Act: -0.1700
Data Index: 6741663 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.7150. Min Act: -0.1700
Data Index: 8705462 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.7150. Min Act: -0.1700
Data Index: 6837357 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.6837. Min Act: -0.1700
Data Index: 6741934 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.6212. Min Act: -0.1700
Data Index: 3208579 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.5900. Min Act: -0.1700
Data Index: 8567857 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.5275. Min Act: -0.1700
Data Index: 6613349 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.4962. Min Act: -0.1700
Data Index: 7168324 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.4650. Min Act: -0.1700
Data Index: 7798430 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.4650. Min Act: -0.1700
Data Index: 5387279 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.4337. Min Act: -0.1700
Data Index: 3825332 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.4650. Min Act: -0.1700
Data Index: 5303704 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.4025. Min Act: -0.1700
Data Index: 7689040 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.4025. Min Act: -0.1700
Data Index: 1812676 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.3712. Min Act: -0.1700
Data Index: 6768012 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.3712. Min Act: -0.1700
Data Index: 8803818 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.3400. Min Act: -0.1700
Data Index: 8229636 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.3712. Min Act: -0.1700
Data Index: 7221815 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9337. Min Range: -7.9337
Max Act: 7.3400. Min Act: -0.1700
Data Index: 6209049 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19